© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28691
    Prev
    Next
    INDEX
    Explanations

    concepts related to housing and its impact on individuals and families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipur
    -0.08
    оваÑĢ
    -0.07
    aal
    -0.06
    ipment
    -0.06
    ossa
    -0.06
    obe
    -0.06
    linger
    -0.06
    ãģ¡ãĤĥ
    -0.06
     integ
    -0.06
    `
    -0.06
    POSITIVE LOGITS
    ancellable
    0.07
    ãĢĩ
    0.07
    $MESS
    0.07
    âĻ¡
    0.07
     ApplicationController
    0.06
    ritt
    0.06
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
     enumerator
    0.06
     automát
    0.06
     Weld
    0.06
    Activations Density 0.042%

    No Known Activations